Effectively Distinguishing Blast and Earthquake Sources in Eastern Canada
DOI:
https://doi.org/10.26443/seismica.v5i1.1964Abstract
Eastern Canada lies within the stable interior of the North American Plate, yet several regions, including the Western Québec, Charlevoix, Lower St. Lawrence, and Northern Appalachians seismic zones, have experienced damaging intraplate earthquakes. Building reliable earthquake catalogs in these regions is challenging because tectonic earthquakes must be distinguished from industrial blasts, often under low signal-to-noise ratio (SNR) conditions. Here we develop a spectrogram-based source discrimination framework using pretrained convolutional neural network (CNN) image classifiers. Approximately 100,000 three-component waveform records of labeled earthquakes and blasts from the Canadian National Earthquake Database (2000-2024) were converted into standardized three-channel spectrogram inputs, and local event origin time was incorporated as an auxiliary feature. Among the tested models, an EfficientNet-based architecture achieved the best overall performance, yielding the lowest weighted classification cost under the imposed minimum-recall constraint. To account for uneven station coverage, we further developed an event-level framework that combines station-level CNN predictions using reliability-based weights derived from source-station distance and denoised SNR. Applied to an enhanced catalog in the Western Québec Seismic Zone, the framework separated blast-like from earthquake-like events while also identifying noise-dominated detections. This reduces false positives introduced by machine-learning based phase picker and helps produce a more reliable regional earthquake catalog. The proposed framework is efficient, transferable, and well suited for catalog enhancement in Eastern Canada, with clear application potential for other intraplate regions.
References
Bottou, L. (2012). Stochastic gradient descent tricks. In Neural Networks: Tricks of the Trade: Second Edition (pp. 421–436). Springer. https://doi.org/10.1007/978-3-642-35289-8_25 DOI: https://doi.org/10.1007/978-3-642-35289-8_25
Brooks, G. R., & Adams, J. (2020). A review of evidence of glacially-induced faulting and seismic shaking in eastern Canada. Quaternary Science Reviews, 228, 106070. https://doi.org/10.1016/j.quascirev.2019.106070 DOI: https://doi.org/10.1016/j.quascirev.2019.106070
Chien, J. (2025). SABER – Spectrogram-based Algorithm for Blast and Earthquake Recognition. [Software]. Zenodo. https://doi.org/10.5281/zenodo.16905883
Ebel, J. E. (2011). A new analysis of the magnitude of the February 1663 earthquake at Charlevoix, Quebec. Bulletin of the Seismological Society of America, 101(3), 1024–1038. https://doi.org/10.1785/0120100190 DOI: https://doi.org/10.1785/0120100190
Ertuncay, D., Lorenzo, A. D., & Costa, G. (2024). Seismic signal discrimination of earthquakes and quarry blasts in North-East Italy using deep neural networks. Pure and Applied Geophysics, 181(4), 1139–1151. https://doi.org/10.1007/s00024-024-03440-0 DOI: https://doi.org/10.1007/s00024-024-03440-0
Gamboa-Canté, C., Arroyo-Solórzano, M., Benito, B., Aguilar, J., Arroyo, I. G., Camacho-Astigarrabia, E., Castro, D., Flores, O., Linkimer, L., Marroquin, M. G., & others. (2024). Seismicity in Central America (1520–2020) and Earthquake catalog compilation for seismic hazard assessments. Bulletin of Earthquake Engineering, 22(15), 7201–7234. https://doi.org/10.1007/978-94-015-9536-0_5 DOI: https://doi.org/10.1007/s10518-024-02059-9
Ghaffari, A., & Savaria, Y. (2020). CNN2Gate: An implementation of convolutional neural networks inference on FPGAs with automated design space exploration. Electronics, 9(12), 2200. https://doi.org/10.3390/electronics9122200 DOI: https://doi.org/10.3390/electronics9122200
Ghosh, A., Holt, W. E., & Bahadori, A. (2019). Role of large-scale tectonic forces in intraplate earthquakes of central and eastern North America. Geochemistry, Geophysics, Geosystems, 20(4), 2134–2156. https://doi.org/10.1029/2018GC008060 DOI: https://doi.org/10.1029/2018GC008060
Hostallero, D. E., Li, Y., & Emad, A. (2022). Looking at the BiG picture: incorporating bipartite graphs in drug response prediction. Bioinformatics, 38(14), 3609–3620. https://doi.org/10.1093/bioinformatics/btac463 DOI: https://doi.org/10.1093/bioinformatics/btac383
Hourcade, C., Bonnin, M., & Beucler, É. (2023). New CNN-based tool to discriminate anthropogenic from natural low magnitude seismic events. Geophysical Journal International, 232(3), 2119–2132. https://doi.org/10.1093/gji/ggac441 DOI: https://doi.org/10.1093/gji/ggac441
Johnson, S. W., Chambers, D. J., Boltz, M. S., & Koper, K. D. (2021). Application of a convolutional neural network for seismic phase picking of mining-induced seismicity. Geophysical Journal International, 224(1), 230–240. https://doi.org/10.1093/gji/ggaa449 DOI: https://doi.org/10.1093/gji/ggaa449
Kao, H., Shan, S.-J., Bent, A., Woodgold, C., Rogers, G., Cassidy, J. F., & Ristau, J. (2012). Regional centroid-moment-tensor analysis for earthquakes in Canada and adjacent regions: An update. Seismological Research Letters, 83(3), 505–515. https://doi.org/10.1785/gssrl.83.3.505 DOI: https://doi.org/10.1785/gssrl.83.3.505
Kasburg, V., Müller, J., Eulenfeld, T., Breuer, A., & Kukowski, N. (2024). Cross-Regional Seismic Event Discrimination via Convolutional Neural Networks: Exploring Fine-Tuning and Ensemble Averaging. Bulletin of the Seismological Society of America, 114(2), 842–856. https://doi.org/10.1785/0120230198 DOI: https://doi.org/10.1785/0120230198
Kim, W.-Y., Simpson, D., & Richards, P. G. (1993). Discrimination of earthquakes and explosions in the eastern United States using regional high-frequency data. Geophysical Research Letters, 20(14), 1507–1510. https://doi.org/10.1029/93GL01267 DOI: https://doi.org/10.1029/93GL01267
Kingma, D. P., & Ba, J. (2014). Adam: A Method for Stochastic Optimization [ArXiv preprint]. https://doi.org/10.48550/arXiv.1412.6980
Koonce, B., & Koonce, B. (2021). EfficientNet. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, 109–123. DOI: https://doi.org/10.1007/978-1-4842-6168-2_10
Korrat, I., Lethy, A., ElGabry, M., Hussein, H., & Othman, A. S. (2022). Discrimination between small earthquakes and quarry blasts in Egypt using spectral source characteristics. Pure and Applied Geophysics, 179(2), 599–618. https://doi.org/10.1007/s00024-022-02953-w DOI: https://doi.org/10.1007/s00024-022-02953-w
Kubo, H., Naoi, M., & Kano, M. (2024). Recent advances in earthquake seismology using machine learning. Earth, Planets and Space, 76(1), 36. https://doi.org/10.1186/s40623-024-01982-0 DOI: https://doi.org/10.1186/s40623-024-01982-0
Lamontagne, M., Brouillette, P., Grégoire, S., Bédard, M., & Bleeker, W. (2020). Faults and lineaments of the western Quebec seismic zone, Quebec and Ontario. Geological Survey of Canada. https://doi.org/10.4095/321900 DOI: https://doi.org/10.4095/321900
Lomax, A., Virieux, J., Volant, P., & Berge-Thierry, C. (2000). Probabilistic earthquake location in 3D and layered models: Introduction of a Metropolis-Gibbs method and comparison with linear locations. In Advances in Seismic Event Location (pp. 101–134). Springer. https://doi.org/10.1007/978-94-015-9536-0_5 DOI: https://doi.org/10.1007/978-94-015-9536-0_5
Loshchilov, I., Hutter, F., & others. (2017). Fixing weight decay regularization in adam. ArXiv Preprint ArXiv:1711.05101, 5.
Ma, S., & Eaton, D. W. (2007). Western Quebec seismic zone (Canada): Clustered, midcrustal seismicity along a Mesozoic hot spot track. Journal of Geophysical Research: Solid Earth, 112(B6). https://doi.org/10.1029/2006JB004827 DOI: https://doi.org/10.1029/2006JB004827
Maguire, R., Schmandt, B., Wang, R., Kong, Q., & Sanchez, P. (2024). Generalization of Deep-Learning Models for Classification of Local Distance Earthquakes and Explosions across Various Geologic Settings. Seismological Research Letters, 95(4), 2229–2238. https://doi.org/10.1785/0220230267 DOI: https://doi.org/10.1785/0220230267
Mancini, S., Segou, M., Werner, M. J., Parsons, T., Beroza, G., & Chiaraluce, L. (2022). On the use of high-resolution and deep-learning seismic catalogs for short-term earthquake forecasts: Potential benefits and current limitations. Journal of Geophysical Research: Solid Earth, 127(11), e2022JB025202. https://doi.org/10.1029/2022JB025202 DOI: https://doi.org/10.1029/2022JB025202
Mazzotti, S., & Townend, J. (2010). State of stress in central and eastern North American seismic zones. Lithosphere, 2(2), 76–83. https://doi.org/10.1130/L65.1 DOI: https://doi.org/10.1130/L65.1
Mousavi, S. M., Ellsworth, W. L., Zhu, W., Chuang, L. Y., & Beroza, G. C. (2020). Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nature Communications, 11(1), 3952. https://doi.org/10.1038/s41467-020-17591-w DOI: https://doi.org/10.1038/s41467-020-17591-w
Münchmeyer, J. (2023). PyOcto: A high-throughput seismic phase associator. ArXiv Preprint ArXiv:2310.11157. https://doi.org/10.26443/seismica.v3i1.1130 DOI: https://doi.org/10.26443/seismica.v3i1.1130
NRCan. (1985). Natural Resources Canada. Canadian National Earthquake Database [Dataset]. Canadian Hazards Information Service. https://doi.org/10.17616/R3TD24
Onwuemeka, J., Liu, Y., & Harrington, R. M. (2018). Earthquake stress drop in the Charlevoix Seismic Zone, eastern Canada. Geophysical Research Letters, 45(22), 12226–12235. https://doi.org/10.1029/2018GL079382 DOI: https://doi.org/10.1029/2018GL079382
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., & others. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32.
Plourde, A. P., & Nedimović, M. R. (2021). Earthquake depths, focal mechanisms, and stress in the Lower St. Lawrence Seismic Zone. Seismological Research Letters, 92(4), 2562–2572. https://doi.org/10.1785/0220200429 DOI: https://doi.org/10.1785/0220200429
Qassim, H., Verma, A., & Feinzimer, D. (2018). Compressed residual-VGG16 CNN model for big data places image recognition. 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), 169–175. https://doi.org/10.1109/CCWC.2018.8301729 DOI: https://doi.org/10.1109/CCWC.2018.8301729
Rakotoarisoa, A. T., & Razafindrakoto, H. N. (2025). Application of Convolutional Neural Networks for Discriminating Anthropogenic and Natural Earthquakes in Madagascar. Bulletin of the Seismological Society of America, 115(4), 1642–1657. https://doi.org/10.1785/0120240244 DOI: https://doi.org/10.1785/0120240244
Reiter, K., Heidbach, O., Schmitt, D., Haug, K., Ziegler, M., & Moeck, I. (2014). A revised crustal stress orientation database for Canada. Tectonophysics, 636, 111–124. https://doi.org/10.1016/j.tecto.2014.08.006 DOI: https://doi.org/10.1016/j.tecto.2014.08.006
Ross, Z. E., Meier, M.-A., Hauksson, E., & Heaton, T. H. (2018). Generalized seismic phase detection with deep learning. Bulletin of the Seismological Society of America, 108(5A), 2894–2901. https://doi.org/10.1785/0120180080 DOI: https://doi.org/10.1785/0120180080
Ruby, U., & Yendapalli, V. (2020). Binary cross entropy with deep learning technique for image classification. Int. J. Adv. Trends Comput. Sci. Eng, 9(10). https://doi.org/10.30534/ijatcse/2020/175942020 DOI: https://doi.org/10.30534/ijatcse/2020/175942020
Targ, S., Almeida, D., & Lyman, K. (2016). Resnet in resnet: Generalizing residual architectures. ArXiv Preprint ArXiv:1603.08029.
Trugman, D. T. (2024). A High-Precision Earthquake Catalog for Nevada. Seismological Research Letters, 95(6), 3737–3745. https://doi.org/10.1785/0220240106 DOI: https://doi.org/10.1785/0220240106
Verdecchia, A., Onwuemeka, J., Liu, Y., & Harrington, R. M. (2022). Depth-dependent crustal stress rotation and strength variation in the Charlevoix seismic zone (CSZ), Québec, Canada. Geophysical Research Letters, 49(22), e2022GL100276. https://doi.org/10.1029/2022GL100276 DOI: https://doi.org/10.1029/2022GL100276
Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I. S., & Xie, S. (2023). ConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16133–16142. https://doi.org/10.1109/CVPR52729.2023.01548 DOI: https://doi.org/10.1109/CVPR52729.2023.01548
Woollam, J., Münchmeyer, J., Tilmann, F., Rietbrock, A., Lange, D., Bornstein, T., Diehl, T., Giunchi, C., Haslinger, F., Jozinović, D., & others. (2022). SeisBench—A toolbox for machine learning in seismology. Seismological Research Letters, 93(3), 1695–1709. https://doi.org/10.1785/0220210324 DOI: https://doi.org/10.1785/0220210324
Yavuz, E., Sertçelik, F., Livaoğlu, H., Woith, H., & Lühr, B.-G. (2019). Discrimination of quarry blasts from tectonic events in the Armutlu Peninsula, Turkey. Journal of Seismology, 23(1), 59–76. https://doi.org/10.1007/s10950-018-9793-2 DOI: https://doi.org/10.1007/s10950-018-9793-2
Zhang, M. (2023). P/SV Amplitude Ratios of Shallow Isotropic Explosions and Earthquakes Could Be Indistinguishable at Local Distances: Insights from Single-Station Waveform Simulations. The Seismic Record, 3(1), 48–56. https://doi.org/10.1785/0320220044 DOI: https://doi.org/10.1785/0320220044
Zhu, J., Fang, L., Miao, F., Fan, L., Zhang, J., & Li, Z. (2024). Deep learning and transfer learning of earthquake and quarry-blast discrimination: applications to southern California and eastern Kentucky. Geophysical Journal International, 236(2), 979–993. https://doi.org/10.1093/gji/ggad463 DOI: https://doi.org/10.1093/gji/ggad463
Zhu, W., & Beroza, G. C. (2019). PhaseNet: a deep-neural-network-based seismic arrival-time picking method. Geophysical Journal International, 216(1), 261–273. https://doi.org/10.1093/gji/ggy423 DOI: https://doi.org/10.1093/gji/ggy423
Zhu, W., Mousavi, S. M., & Beroza, G. C. (2019). Seismic signal denoising and decomposition using deep neural networks. IEEE Transactions on Geoscience and Remote Sensing, 57(11), 9476–9488. https://doi.org/10.1109/TGRS.2019.2926772 DOI: https://doi.org/10.1109/TGRS.2019.2926772
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Justin Chien, Yajing Liu
This work is licensed under a Creative Commons Attribution 4.0 International License.
